boelukas/mariner
(ECCV 2024) MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References
This project helps generate high-quality images from new camera angles using existing rendered images and nearby reference photos. You provide rendered images of a scene from novel viewpoints, along with a set of actual reference images taken from close angles. The tool then outputs enhanced, more realistic images for those new viewpoints. This is ideal for 3D artists, architects, or virtual reality developers who need to produce photorealistic views without extensive manual rendering.
No commits in the last 6 months.
Use this if you need to improve the visual quality and realism of computer-generated images from new perspectives by leveraging real-world photographic references.
Not ideal if you don't have existing rendered images or nearby reference photographs, or if your primary goal is to generate entirely new scenes from scratch without any existing visual input.
Stars
19
Forks
—
Language
Python
License
MIT
Category
Last pushed
Sep 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/boelukas/mariner"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
weiyithu/NerfingMVS
[ICCV 2021 Oral] NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
Jumpat/SegmentAnythingin3D
Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)
POSTECH-CVLab/SCNeRF
[ICCV21] Self-Calibrating Neural Radiance Fields
half-potato/nmf
Our method takes as input a collection of images (100 in our experiments) with known cameras,...
synthesiaresearch/humanrf
Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"